Closed NareshGuru77 closed 5 months ago
Your edits are correct. Sorry for the confusion. We'll fix this bug later.
We have updated the config for few-shot. The custom_keys
in the optimizer also need to be adjusted according to the model size. Hope everything goes well for you.
Hi!, Thank you for the fixes! In the corrected configs, the custom_keys are also already adjusted? I can use them directly?
Thank you!
Yes, you can use them directly. Feel free to ask if you have any other questions.
When using the large and huge few-shot configurations for loveda dataset, since the config uses both the loveda base config and the git_large config, there are overlapping keys. Issue can be resolved by creating a copy of loveda_base and replacing git_base with git_large and load_from base to large.
Is there any other way to fix this? Or am I missing something here?
Thank you!